Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating common or typical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in most cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     some
    -0.46
    دانلود
    -0.42
     Ader
    -0.39
    simpleType
    -0.38
     SOME
    -0.38
     Some
    -0.38
    éndole
    -0.38
    
    -0.37
    setContentType
    -0.37
    Some
    -0.37
    POSITIVE LOGITS
     meestal
    0.73
    generally
    0.73
     generally
    0.71
     meistens
    0.68
    always
    0.66
     usually
    0.65
     Generally
    0.64
    Generally
    0.64
    šinou
    0.63
    Mostly
    0.63
    Act Density 0.013%

    No Known Activations